一种基于帧间差分与背景差分的运动目标检测新方法

针对背景差分算法中在复杂背景下参考帧的提取问题,提出了一种新的运动目标检测方法.该方法基于帧间差分法检测出帧中的背景像素点后,再确立每个点的高斯模型,最后运用背景差分准确检测出场景中的运动目标.由于该方法提取的背景干净,故能有效克服以往检测算法存在的误检和空洞问题.试验结果表明,该方法快速、有效,能够满足运动目标的实时检测要求.

New Moving Objects Detection Method Based on Two Consecutive Frames Subtraction

Aimed at the problem that how to attain background frame in complex condition, a new method to acquire background was presented. Two consecutive frames was subtracted to pick up background pixel in this method, then the Gaussian model of every pixel was built. At last background subtraction was used to detect objects in frame, The algorithm can overcome the mistake and imperfection which were appeared in old moving object detection algorithm. Because cleanly background was attained quickly, the results showed that this algorithm combines the advantages of veracity and of runtime, and fit for real time detection.